Speech recognition based on fuzzy neural network and chaotic differential evolution algorithm

被引：0

作者：

Engineering and Technology College, Hubei University of Technology, Wuhan, China ^{[1
]}

不详 ^{[2
]}

机构：

[1] Engineering and Technology College, Hubei University of Technology, Wuhan

[2] School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan

来源：

J. Inf. Comput. Sci. | / 14卷 / 5451-5458期

关键词：

CDE; Fuzzy neural network; Speech recognition;

D O I：

10.12733/jics20106454

中图分类号：

学科分类号：

摘要：

The training method is very important in speech recognition. But the traditional BP neural network method trained for a long time, easily falling into local extreme disadvantage. However, the optimization algorithm can significant improve the model performance like response speed and recognition accuracy. In this paper, we propose a Chaotic Differential Evolution (CDE) algorithm for optimization the objective function of the fuzzy neural network model in training process, which can effectively improve the accuracy and consistency of speech recognition. The results show that the CDE algorithm optimized fuzzy neural network has more convergence speed and recognition rate than PSO and BP algorithm. Copyright © 2015 Binary Information Press.

引用

页码：5451 / 5458

页数：7

共 11 条

[1]

Rong R., Speech Recognition Using Artificial Neural Networks, (2005)

[2]

Storn R., Price K., Differential Evolution: A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces, (1995)

[3]

Storn R., Price K., Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces, Journal of Global Optimization, 11, 4, pp. 341-359, (1997)

[4]

Lampinen J., Zelinka I., Mixed variable nonlinear optimization by differential evolution, Proceedings of Nostradamus 99, 2nd International Prediction Conference, pp. 45-55, (1999)

[5]

Wu L.H., Wang Y.N., Yuan X.F., Et al., Differential evolution algorithm with adaptive second mutation, Control and Decision, 21, 8, pp. 117-120, (2006)

[6]

Wu L.H., Wang Y.N., Zhou S.W., Yuan X.F., Research and application of pseudo parallel differential evolution algorithm with dual subpopulations, Control Theory & Applications, 24, 3, pp. 453-458, (2007)

[7]

He Y.Y., Zhou J.Z., Xiang X.Q., Et al., Comparison of different chaotic maps in particle swarm optimization algorithm for long term cascaded hydroelectric system scheduling, Chaos Solitons & Fractals, 42, 5, pp. 3169-3176, (2009)

[8]

He Y.Y., Zhou J.Z., Qin H., Mo L., Kou P.G., Flood disaster classification based on fuzzy clustering iterative model and modified differential evolution algorithm, International Conference on Fuzzy Systems and Knowledge Discovery (FSKD09), pp. 85-89, (2009)

[9]

Liao L., Zhou J.Z., Zou Q., Weighted fuzzy kernel-clustering algorithm with adaptive differential evolution and its application on flood classification, Natural Hazards, 69, 1, pp. 279-293, (2013)

[10]

Iyatomi H., Hagiwara M., Adaptive fuzzy inference neural network, Pattern Recognition, 37, 10, pp. 2049-2057, (2004)

← 1 2 →